Tunnel cable inspection system, method, device, computer equipment and storage medium

Abstract

The present application relates to a tunnel cable inspection system, method, device, computer equipment and storage medium. The system includes: a sensor module, a monitoring and control platform, an edge computing node, a big data analysis platform and an inspection robot equipped with multiple sensors: the sensor module collects tunnel cable environmental data and sends it to the edge computing node and the monitoring and control platform; the inspection robot obtains tunnel cable measurement data and sends it to the edge computing node and the monitoring and control platform; the edge computing node performs data preprocessing on the received data, obtains target tunnel cable measurement data and target tunnel cable environmental data and sends them to the big data analysis platform; the big data analysis platform performs fault prediction and health status assessment on the tunnel cable based on the received data, and sends the fault prediction results and health status assessment results to the monitoring and control platform, and the monitoring and control platform performs visual display of the received data. The use of this method is conducive to improving the efficiency of tunnel cable inspection.

Description

Technical Field

[0001] The present application relates to the field of electrical engineering, and in particular to a tunnel cable inspection system, method, device, computer equipment, computer-readable storage medium and computer program product. Background Art

[0002] With the rapid development of science and technology and the continuous advancement of urbanization, the construction scale and standards of modern cities are increasing, and the way of urban power supply is gradually developing towards a more efficient, reliable and beautiful direction. Traditional overhead transmission lines are gradually incompatible with modern urban construction due to their large footprint, wide line corridors, high corona noise, and serious visual pollution, especially in terms of aesthetics and space utilization. In order to optimize the urban environment and improve the reliability of power supply, underground power cables have gradually replaced overhead transmission lines and become the mainstream power supply method.

[0003] Considering that the transmission capacity of a single high-voltage cable can no longer meet the growing load demand. Tunnel cables use double-split cables for transmission to increase transmission capacity. However, when using double-split (same-phase parallel) cables for power transmission, the transmission current of the two sub-cables running in parallel will be unbalanced due to factors of the line itself, mainly including line differentiation caused by differences in path length and manufacturing process, and impedance asymmetry caused by electromagnetic coupling between multiple cables, which are difficult to completely avoid. Under unbalanced working conditions, the split cables in the same phase in parallel may cause different degrees of insulation aging and life differences of the two parallel sub-cables, and even directly lead to thermal breakdown. Mainly due to the complex electromagnetic relationship between cables, the current carrying capacity of the same-phase cable line may be different. This current imbalance will affect the normal operation of power equipment. Therefore, patrol inspections for double-split tunnel cables can discover potential problems, take timely measures to prevent faults, and ensure the stable operation of the power system.

[0004] However, currently, the inspection of tunnel cables mainly relies on manual work, which has the problem of low inspection accuracy. Specifically, in a complex tunnel environment, manual inspections are bound to result in missed inspections or misjudgments. Summary of the invention

[0005] Based on this, it is necessary to provide a tunnel cable inspection method, device, computer equipment, computer readable storage medium and computer program product that can improve tunnel cable inspection in response to the above technical problems.

[0006] In the first aspect, the present application provides a tunnel cable inspection system, including a sensor module, a monitoring and control platform, an edge computing node, a big data analysis platform, and an inspection robot equipped with multiple sensors:

[0007] The sensor module collects tunnel cable environmental data in real time and sends the tunnel cable environmental data to the edge computing node and the monitoring and control platform;

[0008] The inspection robot moves along the preset inspection path, obtains tunnel cable measurement data, and sends the tunnel cable measurement data to the edge computing node and the monitoring and control platform. The tunnel cable measurement data is obtained based on data collected by multiple sensors;

[0009] The edge computing node performs data preprocessing on the tunnel cable measurement data and the tunnel cable environment data to obtain the target tunnel cable measurement data and the target tunnel cable environment data, and sends the target tunnel cable measurement data and the target tunnel cable environment data to the big data analysis platform;

[0010] Based on the target tunnel cable measurement data and target tunnel cable environmental data, the big data analysis platform performs fault prediction and health status assessment on the tunnel cable, obtains the fault prediction results and health status assessment results, and sends the fault prediction results and health status assessment results to the monitoring and control platform, which visualizes the received data.

[0011] In one of the embodiments, the edge computing node is also used to perform abnormality detection on the tunnel cable based on the target tunnel cable measurement data and the target tunnel cable environmental data to obtain an abnormality detection result. When the abnormal result indicates that the tunnel cable is abnormal, an alarm message is generated and sent to the monitoring and control platform.

[0012] In one embodiment, the big data analysis platform is also used to:

[0013] Taking the target tunnel cable measurement data and the target tunnel cable environment data as input, calling a trained fault prediction model to determine the fault prediction time and fault prediction type of the tunnel cable, wherein the trained fault prediction model is trained based on historical target tunnel cable measurement data and historical target tunnel cable environment data;

[0014] Determine a cable health status score based on the target tunnel cable measurement data, the target tunnel cable environment data and a preset health status evaluation standard;

[0015] The predicted fault time, the predicted fault type and the cable health status score are sent to the monitoring and control platform.

[0016] In one embodiment, the sensor module includes a temperature sensor, a humidity sensor, a vibration sensor, and a current sensor:

[0017] The temperature sensor is used to collect temperature data of the tunnel cable and send the temperature data to the edge computing node;

[0018] The humidity sensor is used to collect humidity data of the tunnel cable and send the humidity data to the edge computing node;

[0019] The vibration sensor is used to collect vibration data of the tunnel cable and send the vibration data to the edge computing node;

[0020] The current sensor is used to collect current data of the tunnel cable and send the current data to the edge computing node. The tunnel cable environmental data includes the temperature data, humidity data, vibration data and current data.

[0021] In one embodiment, the inspection robot is equipped with a temperature sensor, a humidity sensor, a current sensor, a voltage sensor, a smoke sensor and an image sensor:

[0022] The temperature sensor is used to collect temperature data of the tunnel cable and send the temperature data to the edge computing node;

[0023] The humidity sensor is used to collect humidity data of the tunnel cable and send the humidity data to the edge computing node;

[0024] The current sensor is used to collect current data of the tunnel cable and send the current data to the edge computing node;

[0025] The voltage sensor is used to collect voltage data of the tunnel cable and send the voltage data to the edge computing node;

[0026] The smoke sensor is used to collect smoke concentration data in the tunnel and send the smoke concentration data to the edge computing node;

[0027] The image sensor is used to collect image data of the tunnel cable and send the image data to the edge computing node;

[0028] The tunnel cable measurement data includes the temperature data, humidity data, voltage data and current data, concentration data and image data.

[0029] In one embodiment, the inspection robot is also equipped with a laser radar sensor and an ultrasonic sensor, wherein:

[0030] The laser radar sensor and ultrasonic sensor are used to detect whether there are obstacles in the preset inspection path and obtain obstacle detection results. The inspection robot is also used to perform obstacle avoidance operations based on the obstacle detection results.

[0031] In one of the embodiments, the big data analysis platform generates maintenance suggestion information based on the predicted fault time and the predicted fault type, and sends the maintenance suggestion information to the monitoring and control platform.

[0032] In one of the embodiments, the monitoring and control platform is also used to push alarm information after receiving the alarm information.

[0033] In one embodiment, the monitoring and control platform further includes a control module, and the control module is used to remotely control the inspection robot.

[0034] In a second aspect, the present application provides a tunnel cable inspection method, which is applied to a big data analysis platform of the tunnel cable inspection system, comprising:

[0035] Acquire tunnel cable measurement data and tunnel cable environment data, where the tunnel cable measurement data and the tunnel cable environment data are obtained based on data collected by multiple sensors;

[0036] Taking the tunnel cable measurement data and the tunnel cable environment data as input, calling the trained fault prediction model to determine the fault prediction time and fault prediction type of the tunnel cable, the fault prediction model is trained based on the historical tunnel cable measurement data and the historical tunnel cable environment data carrying the fault time point and fault type;

[0037] Determine the cable health status score based on the tunnel cable measurement data, tunnel cable environment data and preset health status evaluation standards;

[0038] Early warning is provided based on fault prediction time, fault prediction type and cable health status score.

[0039] In a third aspect, the present application also provides a tunnel cable inspection device, comprising:

[0040] A data acquisition module, used to acquire tunnel cable measurement data and tunnel cable environment data, wherein the tunnel cable measurement data and tunnel cable environment data are obtained based on data collected by multiple sensors;

[0041] A fault prediction module is used to use tunnel cable measurement data and tunnel cable environment data as input, call a trained fault prediction model, and determine the fault prediction time and fault prediction type of the tunnel cable. The fault prediction model is trained based on historical tunnel cable measurement data and historical tunnel cable environment data that carry fault time points and fault types.

[0042] A health assessment module, used to determine the cable health status score based on the tunnel cable measurement data, tunnel cable environment data and preset health status evaluation criteria;

[0043] The fault warning module is used to issue warnings based on the fault prediction time, fault prediction type and cable health status score.

[0044] In a fourth aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps in the above-mentioned tunnel cable inspection method embodiment when executing the computer program.

[0045] In a fifth aspect, the present application further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned tunnel cable inspection method embodiment are implemented.

[0046] In a sixth aspect, the present application further provides a computer program product, including a computer program, which, when executed by a processor, implements the steps in the above-mentioned tunnel cable inspection method embodiment.

[0047] The above-mentioned tunnel cable inspection system, on the one hand, compared with the traditional manual cable inspection method, forms an efficient cable inspection and management system through the close cooperation of various components of the tunnel cable inspection system, adopts automated robot inspection and all-weather monitoring, greatly improves the inspection efficiency, ensures the comprehensiveness and timeliness of cable maintenance, reduces the possibility of missed inspections and personnel costs of manual inspections, and improves the accuracy and safety of inspections; on the other hand, it collects cable measurement data during the inspection process through multiple sensors, and performs fault prediction and cable health status assessment based on multi-dimensional cable measurement data, so as to improve the accuracy of prediction and assessment results and adapt to the complex environment in the tunnel, which is conducive to taking corresponding preventive measures according to accurate prediction results and assessment results, reducing the possibility of sudden failures and cable power outages, and improving the stability and reliability of power transmission. At the same time, fault prediction is conducive to reducing the maintenance cost of major failures. On the other hand, the intelligent tunnel cable system has high scalability and high availability, and can be continuously optimized and upgraded according to future technological development trends to adapt to more complex tunnel environments, which is conducive to improving the convenience of tunnel current inspection management and optimization.

[0048] The above-mentioned tunnel cable inspection method, device, computer equipment, computer-readable storage medium and computer program product. By using the tunnel cable measurement data and tunnel cable environmental data obtained based on data collected by multiple sensors, the trained fault prediction model is called to determine the fault prediction time and fault prediction type of the tunnel cable, thereby improving the accuracy of fault prediction, which is conducive to tunnel cable management and maintenance based on the fault prediction time and fault prediction type to reduce the probability of fault occurrence. Based on the tunnel cable measurement data, tunnel cable environmental data and preset health status evaluation standards, the cable health status score is determined, which is conducive to timely maintenance of the cable according to the cable health status score, ensuring the reliability of the tunnel power system operation. Early warning is issued based on the fault prediction time, fault prediction type and cable health status score to remind maintenance personnel to perform tunnel cable maintenance, which is conducive to ensuring the safe operation of the cable. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 is a structural block diagram of a tunnel cable inspection system in one embodiment;

[0051] Figure 2 is a structural block diagram of a tunnel cable inspection system in another embodiment;

[0052] Figure 3 This is an application environment diagram of a tunnel cable inspection method in one embodiment;

[0053] Figure 4 A schematic diagram of a process of a tunnel cable inspection method in one embodiment;

[0054] Figure 5 is a structural block diagram of a tunnel cable inspection device in one embodiment;

[0055] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0057] In an exemplary embodiment, Figure 1 As shown, a tunnel cable inspection system is provided, including a sensor module 110, a monitoring and control platform 120, an edge computing node 130, a big data analysis platform 140, and an inspection robot 150 equipped with multiple sensors, wherein:

[0058] The sensor module 110 collects tunnel cable environment data in real time and sends the tunnel cable environment data to the edge computing node 130 and the monitoring and control platform 120 .

[0059] Among them, the sensor module can be deployed at different locations along the cable in the tunnel to facilitate real-time monitoring of the status of the cable body and its surrounding environment. Tunnel cable environmental data may include but is not limited to temperature data and humidity data. The edge computing node is deployed at a key location in the tunnel, close to the data source (sensor module), and the number of edge computing nodes can be multiple. The edge computing node is used to pre-process the received data, reduce the pressure on the big data analysis platform, and improve the real-time performance of data processing. The detection and control platform is used to monitor the operating status of the tunnel inspection system in real time, store and visualize the received data, etc. In actual applications, the sensor module can collect tunnel cable environmental data in real time and send the tunnel cable environmental data to the edge computing node through the data interface. The tunnel cable environmental data is sent to the monitoring and control platform through the network.

[0060] The inspection robot 150 moves along a preset inspection path, obtains tunnel cable measurement data, and sends the tunnel cable measurement data to the edge computing node 130 and the monitoring and control platform 120. The tunnel cable measurement data is obtained based on data collected by multiple sensors.

[0061] Among them, the inspection robot is used to comprehensively monitor the cable and the tunnel environment around the cable, and collect tunnel cable measurement data. Tunnel cable measurement data may include but is not limited to temperature data, humidity data, current data and voltage data. In practical applications, the inspection path of the inspection robot can be pre-set, and the tunnel cable inspection command can be issued to the inspection robot through the inspection robot controller. The inspection robot responds to the tunnel cable inspection command and moves in the tunnel according to the preset inspection path through GPS, inertial navigation system or other positioning technology. During the inspection process, the tunnel cable measurement data is obtained through the onboard sensors, and the tunnel cable measurement data is sent to the edge computing node and the monitoring and control platform.

[0062] The edge computing node 130 performs data preprocessing on the tunnel cable measurement data and the tunnel cable environment data to obtain the target tunnel cable measurement data and the target tunnel cable environment data, and sends the target tunnel cable measurement data and the target tunnel cable environment data to the big data analysis platform 140 .

[0063] Among them, data preprocessing includes but is not limited to data cleaning, data filtering and format conversion, etc. Data cleaning can include missing value processing, noise data removal and duplicate data processing, etc.

[0064] In actual applications, after receiving the tunnel cable measurement data and tunnel cable environment data, the edge computing node performs data preprocessing such as data cleaning, data filtering and format conversion on the tunnel cable measurement data and tunnel cable environment data to obtain the target tunnel cable measurement data and target tunnel cable environment data, and send them to the big data analysis platform.

[0065] The big data analysis platform 140 performs fault prediction and health status assessment on the tunnel cable based on the target tunnel cable measurement data and the target tunnel cable environmental data, obtains the fault prediction results and the health status assessment results, and sends the fault prediction results and the health status assessment results to the monitoring and control platform 120, which visualizes the received data.

[0066] The fault prediction result may include the fault prediction type. The health status assessment result may include whether the health status of the cable operation is healthy, whether the cable load is healthy, whether the cable insulation and conductor are healthy, and whether the cable insulation layer environment is healthy.

[0067] In practical applications, the big data analysis platform stores the target tunnel cable measurement data and target tunnel cable environment data within the historical time period, and the corresponding fault types, which may include short circuit, overheating, insulation failure and no fault, etc. After the big data analysis platform receives the target tunnel cable measurement data and the target tunnel cable environment data, it can use statistical methods, such as time series analysis methods, based on the historical data, target tunnel cable measurement data and target tunnel cable environment data stored locally to capture the data change trends of different fault types, perform fault prediction, and obtain fault prediction results. The health status assessment based on the target tunnel cable measurement data and the target tunnel environment data can be to set a standard data range for each type of data in the target tunnel cable measurement data and the target tunnel environment data, and determine the health status assessment result based on whether the data is within the corresponding standard data range. For example, if the voltage data is within the corresponding standard data range, the cable is in a healthy state, otherwise the cable is in an unhealthy state; if the current data is within the corresponding standard data range, the cable load is healthy, otherwise the cable load is unhealthy; if the temperature data is within the corresponding standard data range, the cable insulation and conductor are healthy, otherwise the cable insulation and conductor are unhealthy; if the humidity data is within the corresponding standard data range, the cable insulation layer environment is healthy, otherwise the cable insulation layer environment is unhealthy. The fault prediction results and health status assessment results are sent to the monitoring and control platform.

[0068] The monitoring and control platform is the user interface of the tunnel inspection system, which is used to integrate all data and operation information in the system and provide visualization services. Specifically, it is used to display temperature, humidity, current and other data during the operation of the cable in real time, and to perform visualization based on the received data, such as generating charts and trend charts, to help managers understand the operation status of the cable more intuitively. The monitoring and control platform is also used to query historical inspection data, review the cable operation history and system maintenance records.

[0069] In this embodiment, on the one hand, compared with the traditional manual cable inspection method, the various components of the tunnel cable inspection system are closely coordinated to form an efficient cable inspection and management system, and the use of automated robot inspection and all-weather monitoring greatly improves the inspection efficiency, ensures the comprehensiveness and timeliness of cable maintenance, reduces the possibility of missed inspections and personnel costs in manual inspections, and improves the accuracy and safety of inspections; on the other hand, multiple sensors are used to collect cable measurement data during the inspection process, and fault prediction and cable health status evaluation are performed based on multi-dimensional cable measurement data, so as to improve the accuracy of prediction and evaluation results according to the prediction results and adapt to the complex environment in the tunnel, which is conducive to taking corresponding preventive measures according to accurate prediction results and evaluation results, reducing the possibility of sudden failures and cable power outages, and improving the stability and reliability of power transmission. At the same time, fault prediction is conducive to reducing the maintenance cost of major failures. On the other hand, the intelligent tunnel cable system has high scalability and high availability, and can be continuously optimized and upgraded according to future technological development trends to adapt to more complex tunnel environments, which is conducive to improving the convenience of tunnel current inspection management and optimization.

[0070] In an exemplary embodiment, the edge computing node 130 is also used to perform anomaly detection on the tunnel cable based on the target tunnel cable measurement data and the target tunnel cable environment data to obtain anomaly detection results, and when the anomaly results indicate that the tunnel cable has an abnormality, an alarm message is generated and sent to the monitoring and control platform.

[0071] The alarm information may include the abnormality type and the time when the abnormality occurred. The target tunnel cable environmental data includes temperature data, humidity data, vibration data and current data; the target tunnel cable measurement data includes temperature data, humidity data, current data, voltage data, smoke concentration data and image data.

[0072] In practical applications, corresponding abnormality detection thresholds can be set in advance for temperature data, humidity data, vibration data, current data, voltage data, and smoke concentration data. The abnormality detection threshold can be set according to the power industry standard or according to historical data and experience. When there is target tunnel environment data or target tunnel measurement data that exceeds the corresponding abnormality detection threshold, it is determined that there is an abnormality, and the abnormality type and abnormality occurrence time are recorded. The abnormality type may include excessive temperature, excessive humidity, abnormal current, abnormal voltage, excessive smoke concentration, and excessive vibration. Exemplarily, if the temperature data exceeds the corresponding abnormality detection threshold, the abnormality type may include excessive temperature, which may be a precursor to faults such as cable overload and insulation failure; if the humidity data exceeds the corresponding abnormality detection threshold, the abnormality type may include excessive humidity, which has a great impact on the insulation performance of the cable, especially in a high humidity environment, the cable may cause the insulation performance to decrease due to moisture absorption, increasing the risk of leakage; if the current data exceeds the corresponding abnormality detection threshold, the abnormality type may include abnormal current, and the excessive current may accelerate the aging of the cable and even cause a fire hazard. The alarm information is generated according to the abnormality type and the time when the abnormality occurs. The alarm information can also include the abnormal data, and the alarm information is sent to the monitoring and control platform through the communication module.

[0073] The edge computing node also includes 4G / 5G wireless communication modules and fiber optic communication modules, which are used to transmit data to big data analysis nodes and monitoring and control platforms. Through the combination of different communication methods, the coverage of the communication network for tunnel cable inspection can be expanded to ensure the transmission timeliness and integrity of the data during the inspection.

[0074] In this embodiment, the edge computing node performs preliminary anomaly detection, which is conducive to timely discovery of potential fault risks, thereby facilitating the timeliness of tunnel power system maintenance, and further facilitating the reliability of tunnel power system operation.

[0075] In an exemplary embodiment, the big data analysis platform 140 is further used to:

[0076] Taking the target tunnel cable measurement data and the target tunnel cable environmental data as input, calling the trained fault prediction model, determining the fault prediction time and fault prediction type of the tunnel cable, the trained fault prediction model is trained based on the historical target tunnel cable measurement data and the historical target tunnel cable environmental data.

[0077] Among them, fault prediction types may include short circuit, breakdown fault, current overload, poor contact, insulation aging and fire.

[0078] In practical applications, the fault prediction model can be pre-trained on a big data analysis platform. Specifically, the target tunnel cable measurement data and the target tunnel cable environmental data within a historical time period can be obtained for data annotation, and the annotation information is used to indicate whether a fault has occurred, the time point of the fault, and the type of fault. An initial fault prediction model is pre-built based on a regression model and a convolutional neural network. The neural network model includes but is not limited to linear regression, logistic regression, and ARIMA models. By iteratively training the initial fault prediction model, the fault development trend is learned until the preset training end condition is reached, and a trained fault prediction model is obtained. Among them, the preset training end condition can be that the loss function value is less than a preset loss threshold for a consecutive preset number of times. Taking the target tunnel cable measurement data and the target tunnel cable environmental data as input, the trained fault prediction model is called to output the fault prediction time and fault prediction type of the tunnel cable.

[0079] The big data analysis platform 140 determines the cable health status score based on the target tunnel cable measurement data, the target tunnel cable environment data and the preset health status evaluation standard.

[0080] In practical applications, each type of data in the target tunnel cable measurement data and the target tunnel cable environment data is used as a health status evaluation indicator, and a corresponding standard data range is set for each health status evaluation indicator, and the standard data range represents a normal data range. Each health status evaluation indicator is scored by a preset health status evaluation standard to obtain a score for each health status indicator, and a weight is assigned to each score, and the health status score of the cable is obtained by weighted fusion. Specifically, the preset health status evaluation standard can be that for each health status evaluation indicator, if the data corresponding to the health status rating indicator is within the standard data range, its score is 70 to 100 points, and the corresponding score exceeding the upper limit of the standard data range is 0 to 69 points. Weights are assigned to each score. For example, the weight of temperature data is 0.15, the weight of humidity data is 0.3, the weight of current data is 0.2, the weight of voltage data is 0.15, the weight of smoke concentration data is 0.1, and the weight of vibration data is 0.1.

[0081] The big data analysis platform 140 sends the fault prediction time, fault prediction type and cable health status score to the monitoring and control platform.

[0082] In this embodiment, on the one hand, through the powerful computing power of the big data analysis platform, a large amount of target tunnel cable measurement data and target tunnel cable environmental data are processed in real time to perform cable fault prediction and health status assessment, thereby improving data processing efficiency and real-time performance; on the other hand, fault prediction and health status assessment are performed through multi-dimensional tunnel cable data, thereby improving the accuracy of fault prediction and health status assessment, thereby improving the accuracy of inspection.

[0083] In an exemplary embodiment, the sensor module 110 includes a temperature sensor 111, a humidity sensor 112, a vibration sensor 113 and a current sensor 114. Among them:

[0084] The temperature sensor 111 is used to collect temperature data of the tunnel cable and send the temperature data to the edge computing node 130 .

[0085] Among them, the temperature sensor is used to monitor the temperature changes of the cable, collect temperature data and send it to the edge computing node, so that the edge computing node can analyze whether the cable is overheated through the temperature data.

[0086] The humidity sensor 112 collects humidity data of the tunnel cable and sends the humidity data to the edge computing node 130 .

[0087] Among them, the humidity sensor is used to detect the humidity in the tunnel, collect humidity data and send it to the edge computing node, so that the edge computing node can analyze whether the humidity in the tunnel is too high through the humidity data.

[0088] The vibration sensor 113 is used to collect vibration data of the tunnel cable and send the vibration data to the edge computing node 130 .

[0089] Among them, vibration sensors are used to monitor the vibration of cables or tunnel structures. They can capture mechanical vibrations or stress changes in the external environment, collect vibration data and send them to edge computing nodes so that the edge computing nodes can analyze the vibration data and detect possible structural damage in a timely manner.

[0090] The current sensor 114 is used to collect current data of the tunnel cable and send the current data to the edge computing node 130. The tunnel cable environmental data includes temperature data, humidity data, vibration data and current data.

[0091] Among them, the current sensor is used to monitor the current fluctuations of the cable, collect current data and send it to the edge computing node so that the edge computing node can identify abnormal current conditions.

[0092] In other embodiments, the sensor network further includes a communication module 115, which uses communication technology to transmit the data collected by each sensor in the sensor network to the edge computing node through the communication technology. Exemplarily, in order to improve the accuracy of sensor data transmission, the communication module uses Zigbee technology for data transmission. Zigbee is a low-speed, short-distance transmission wireless network protocol with low power consumption and strong anti-interference ability.

[0093] In this embodiment, by deploying a sensor network in the tunnel and collecting multi-dimensional sensor data to monitor the environmental status in the tunnel in real time, it is beneficial to improve the efficiency of inspections, reduce the possibility of missed inspections, and ensure the comprehensiveness and timeliness of cable maintenance.

[0094] In an exemplary embodiment, Figure 2 As shown, the inspection robot 150 is equipped with a temperature sensor 151, a humidity sensor 152, a current sensor 153, a voltage sensor 154, a smoke sensor 155 and an image sensor 156, wherein:

[0095] The temperature sensor 151 is used to collect temperature data of the tunnel cable and send the temperature data to the edge computing node 130 .

[0096] Among them, the temperature sensor is used to monitor the temperature changes inside the tunnel and on the surface of the cable, especially in the area where the cable is heated, and the temperature sensor collects temperature data. Abnormal temperature rise is a precursor to faults such as cable overload and insulation failure.

[0097] The humidity sensor 152 is used to collect humidity data of the tunnel cable and send the humidity data to the edge computing node 130 .

[0098] The humidity sensor is used to collect humidity data in the air inside the tunnel and send the collected humidity data to the edge computing node. Humidity has a great impact on the insulation performance of the cable, especially in a high humidity environment, the insulation performance of the cable may decrease due to moisture absorption, increasing the risk of leakage.

[0099] The current sensor 153 is used to collect current data of the tunnel cable and send the current data to the edge computing node 130 .

[0100] Among them, the current sensor is used to detect the actual load status of the cable, collect the current data of the cable and send it to the edge computing node.

[0101] The voltage sensor 154 is used to collect voltage data of the tunnel cable and send the voltage data to the edge computing node 130 .

[0102] Among them, the voltage sensor is used to monitor the voltage fluctuations at both ends of the cable, collect the voltage data of the cable and send it to the edge computing node.

[0103] The smoke sensor 155 is used to collect smoke concentration data in the tunnel and send the smoke concentration data to the edge computing node.

[0104] Among them, the smoke sensor is used to detect the smoke concentration in the tunnel, collect smoke concentration data and send it to the edge computing node so that the edge computing node can detect possible fire hazards.

[0105] The image sensor 156 is used to collect image data of the tunnel cable and send the image data to the edge computing node 130. The tunnel cable measurement data includes temperature data, humidity data, voltage data and current data, concentration data and image data.

[0106] The image sensor can be a high-resolution camera that is used to capture images of the cable surface, cable brackets, and tunnel walls in the tunnel, and can capture subtle physical damage, such as cable sheath rupture, bracket deformation, etc. The image sensor collects image data and sends it to the edge computing node.

[0107] In other embodiments, considering the long time and long distance of tunnel cable inspection, the inspection robot also includes a LoRa communication module, which is used to transmit the tunnel cable measurement data to the edge computing node in the tunnel through the LoRa communication technology to achieve efficient communication. At the same time, the low power consumption characteristics of LoRa enable the inspection robot to work continuously for a long time, which is suitable for long-distance tunnel environments.

[0108] In this embodiment, tunnel cable inspection is performed by an inspection robot equipped with multiple sensors. On the one hand, the multi-dimensional tunnel cable measurement data collected by multiple sensors is conducive to improving the accuracy and comprehensiveness of tunnel cable inspection, thereby ensuring the operating stability and safety of the tunnel power system; on the other hand, different from the traditional manual inspection method, the automated inspection method of the inspection robot improves the inspection efficiency of the tunnel cable and reduces the cost and complexity of manual inspection.

[0109] In an exemplary embodiment, the inspection robot 150 is also equipped with a laser radar sensor 157 and an ultrasonic sensor 158.

[0110] The laser radar sensor 157 and the ultrasonic sensor 158 are used to detect whether there are obstacles in the preset inspection path and obtain obstacle detection results. The inspection robot 150 is also used to perform obstacle avoidance operations based on the obstacle detection results.

[0111] The obstacle detection result may include the location and distance of the obstacle. In actual applications, the inspection robot emits ultrasonic waves and laser beams through lidar sensors and ultrasonic sensors, and measures the location and distance of the obstacle based on the emitted light signals and reflected waves. When the obstacle detection result indicates the existence of an obstacle, the optimal path to avoid the obstacle is calculated based on the location and distance of the obstacle through the built-in autonomous obstacle avoidance function, and obstacle avoidance operations are performed to improve the reliability of inspections in complex tunnel environments.

[0112] In other embodiments, the preset inspection path also includes markings of specific areas. The inspection robot can increase the inspection frequency of specific areas in the inspection path based on the markings of specific areas in the preset inspection path. The specific areas may be areas where cable joints are located and areas with high incidence of cable failures, so as to improve the accuracy and reliability of the inspection.

[0113] In this embodiment, the inspection robot automatically performs obstacle avoidance operations based on the fault monitoring results of the laser radar sensor and the ultrasonic sensor, thereby improving its adaptability to inspections in complex tunnel environments and the reliability of tunnel cable inspections.

[0114] In an exemplary embodiment, the big data analysis platform 140 is also used to generate maintenance suggestion information based on the predicted fault time and the predicted fault type, and send the maintenance suggestion information to the monitoring and control platform.

[0115] Among them, the maintenance recommendation information includes maintenance measures corresponding to the fault prediction type. For example, if the fault prediction type is insulation aging, the maintenance measures may be to use visual inspection equipment, ultrasonic flaw detectors, etc. to check whether the outer protective layer of the cable is damaged, and to repair or replace the damaged part; if the fault prediction type is short circuit, the corresponding maintenance measures may be to use high-voltage testing equipment, partial discharge detectors, etc. to locate the fault point, and repair or replace damaged conductors and insulation materials; if the fault prediction type is poor contact, the corresponding maintenance measures may be to use an infrared thermal imager to check the cable connection points and terminals to ensure good contact, and clean or replace overheating components; if the fault prediction type is excessive humidity, the corresponding maintenance measures may be to strengthen sealing measures and install moisture-proof devices.

[0116] In this embodiment, maintenance recommendation information is generated through fault prediction results and sent to the monitoring and control platform to inform monitoring personnel of the potential failure risks of the tunnel cable and take corresponding maintenance measures based on the maintenance recommendation information, which is beneficial to improving the timeliness of fault prevention and preventive maintenance efficiency of the tunnel cable.

[0117] In an exemplary embodiment, the monitoring and control platform 120 is further configured to push alarm information after receiving the alarm information.

[0118] In actual applications, the method of pushing alarm information may include pushing alarm information in the notification bar of the monitoring and control platform, displaying the alarm information in the form of a full-screen or half-screen pop-up window, issuing an alarm prompt by emitting a specific sound or vibration mode, providing a visual alarm prompt by flashing an indicator light, etc. It can be understood that the method of pushing alarm information can be any one of the aforementioned methods or a combination of any two or more methods, and is not limited here.

[0119] In this embodiment, by pushing alarm information, the operation and maintenance personnel can be reminded in time to perform corresponding processing, thereby improving the timeliness of tunnel cable operation and maintenance, which is beneficial to improving the operational safety of the tunnel power system.

[0120] In other embodiments, the monitoring and control platform 120 is also used to generate a fault report based on the time, location and type of the fault when receiving the alarm information, so as to provide a basis for fault handling.

[0121] In an exemplary embodiment, the detection control platform further includes a control module, and the control module is used to remotely control the inspection robot.

[0122] The control module is a mobile application that provides a more convenient operation method for operation and maintenance personnel. Even if they are far away from the monitoring center, operation and maintenance personnel can view the tunnel cable measurement data and tunnel cable environment data in real time through the control software and monitor the working status of the inspection robot.

[0123] When an alarm message is received, the control module can send remote commands to the inspection robot to control the inspection robot to go deep into the fault area for further inspection and data collection.

[0124] In this embodiment, the control software can improve the convenience of operation and maintenance personnel in monitoring the status of tunnel cables, improve the convenience of controlling the inspection robot, and at the same time, the accuracy and effectiveness of tunnel cable inspections are improved by controlling the inspection robot.

[0125] Based on the same inventive concept, the present application also provides a tunnel cable inspection method, which can be applied to Figure 3 In the application environment shown, the edge computing node 102 communicates with the big data analysis platform 104 through the network. The data storage system can store the data that the big data analysis platform 104 needs to process. The data storage system can be integrated on the big data analysis platform 104, or it can be placed on the cloud or other network servers.

[0126] Specifically, the edge computing node 102 may upload the collected target tunnel cable measurement data and target tunnel cable environmental data to the big data analysis platform 104, and the big data analysis platform 104 obtains the target tunnel cable measurement data and the target tunnel cable environmental data, and then uses the tunnel cable measurement data and the target tunnel cable environmental data as input to call the trained fault prediction model to determine the fault prediction time and fault prediction type of the tunnel cable, and then determines the cable health status score based on the tunnel cable measurement data, the target tunnel cable environmental data and the preset health status evaluation standard, and finally, issues an early warning based on the fault prediction time, fault prediction type and cable health status level.

[0127] The edge computing node 102 may be, but is not limited to, various personal computers, laptops, smart phones, and tablet computers, etc. The big data analysis platform 104 may be an independent physical server, a server cluster or a distributed system consisting of multiple physical servers, or a cloud server that provides cloud computing services.

[0128] In an exemplary embodiment, Figure 4 As shown, a tunnel cable inspection method is provided, which is applied to Figure 3 The big data analysis platform 104 in FIG. 1 is used as an example to illustrate the process, which includes the following S100 to S400. Among them:

[0129] S100, obtaining tunnel cable measurement data and tunnel cable environment data, where the tunnel cable measurement data and the tunnel cable environment data are obtained based on data collected by multiple sensors.

[0130] The tunnel cable measurement data may include the current data and voltage data of the cable. The tunnel cable environment data may include temperature data, humidity data, smoke concentration data and vibration data.

[0131] In practical applications, the data can be collected through temperature sensors, humidity sensors, current sensors, voltage sensors, vibration sensors and smoke sensors deployed in the tunnel, or by acquiring data collected by inspection robots equipped with temperature sensors, humidity sensors, current sensors, voltage sensors, smoke sensors and vibration sensors.

[0132] S200, taking the tunnel cable measurement data and the tunnel cable environment data as input, calling the trained fault prediction model, determining the fault prediction time and fault prediction type of the tunnel cable, the fault prediction model is trained based on the historical tunnel cable measurement data and the historical tunnel cable environment data carrying the fault time point and fault type.

[0133] In practical applications, it is possible to obtain tunnel cable measurement data and tunnel cable environment data within a historical time period for data annotation, and the annotation information is used to indicate whether a fault has occurred, the time point of the fault, and the type of fault. An initial fault prediction model is pre-built based on a regression model and a convolutional neural network. The neural network model includes but is not limited to linear regression, logistic regression, and ARIMA models. The initial fault prediction model is iteratively trained to learn the fault development trend until the preset training end condition is reached, and a trained fault prediction model is obtained. Among them, the preset training end condition can be that the loss function value is less than a preset loss threshold for a preset number of consecutive times.

[0134] After obtaining the trained fault prediction model, the tunnel cable measurement data and tunnel cable environment data are used as input to call the trained fault prediction model and output the fault prediction time and fault prediction type of the tunnel cable.

[0135] S300, determining a cable health status score based on tunnel cable measurement data, tunnel cable environment data and a preset health status evaluation standard.

[0136] In practical applications, each type of data in the tunnel cable measurement data and the tunnel cable environment data can be used as a health status evaluation indicator, and a corresponding standard data range is set for each health status evaluation indicator, and the standard data range represents a normal data range. Each health status evaluation indicator is scored by a preset health status evaluation standard to obtain a score for each health status indicator, and a weight is assigned to each score, and the health status score of the cable is obtained by weighted fusion. Specifically, the preset health status evaluation standard can be that for each health status evaluation indicator, if the data corresponding to the health status rating indicator is within the standard data range, its score is 70 to 100 points, and the corresponding score exceeding the upper limit of the standard data range is 0 to 69 points. Weights are assigned to each score. For example, the weight of temperature data is 0.15, the weight of humidity data is 0.3, the weight of current data is 0.2, the weight of voltage data is 0.15, the weight of smoke concentration data is 0.1, and the weight of vibration data is 0.1.

[0137] S400, early warning based on fault prediction time, fault prediction type and cable health status score.

[0138] In practical applications, a health status score threshold can be pre-set based on historical fault records. When the cable health status score is lower than the preset health status score threshold (such as 70 points), each type of data and score in the tunnel cable measurement data and tunnel cable environment data, as well as the cable health status score, are integrated to obtain early warning information for early warning. A time interval threshold (such as 15 days) is pre-set. When the fault prediction time is not greater than the preset time interval, maintenance recommendations are generated based on the fault prediction time and fault prediction type. The fault prediction time, fault prediction type and maintenance recommendations are integrated to obtain early warning information for early warning. Among them, maintenance suggestions are generated according to the fault prediction time and the fault prediction type. For example, the maintenance suggestion information includes maintenance measures corresponding to the fault prediction type. For example, if the fault prediction type is insulation aging, the maintenance measures may be to use visual inspection equipment, ultrasonic flaw detectors, etc. to check whether the outer protective layer of the cable is damaged, and repair or replace the damaged part; if the fault prediction type is short circuit, the corresponding maintenance measures may be to use high-voltage testing equipment, partial discharge detectors, etc. to locate the fault point, and repair or replace the damaged conductor and insulation material; if the fault prediction type is poor contact, the corresponding maintenance measures may be to use infrared thermal imagers to check the cable connection points and terminals to ensure good contact, clean or replace overheating components; if the fault prediction type is too high humidity, the corresponding maintenance measures may be to strengthen sealing measures and install moisture-proof devices. The method of pushing the warning information may include displaying the warning information on a display, issuing a warning prompt by emitting a specific sound or vibration mode, and providing a visual warning prompt by flashing an indicator light, etc. It can be understood that the method of pushing the warning information may be any one of the aforementioned methods or a combination of any multiple methods.

[0139] In the above-mentioned tunnel cable inspection method, the tunnel cable measurement data and tunnel cable environmental data obtained based on data collected by multiple sensors are used to call the trained fault prediction model to determine the fault prediction time and fault prediction type of the tunnel cable, thereby improving the accuracy of fault prediction and facilitating tunnel cable management and maintenance based on the fault prediction time and fault prediction type to reduce the probability of fault occurrence. Based on the tunnel cable measurement data, tunnel cable environmental data and preset health status evaluation standards, the cable health status score is determined, which is conducive to timely maintenance of the cable based on the cable health status score and ensuring the reliability of the tunnel power system operation. Early warning is issued based on the fault prediction time, fault prediction type and cable health status score to remind maintenance personnel to perform tunnel cable maintenance, which is conducive to ensuring the safe operation of the cable.

[0140] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0141] In an exemplary embodiment, Figure 5 As shown, a tunnel cable inspection device 600 is provided, comprising: a data acquisition module 610, a fault prediction module 620, a health assessment module 630 and a fault warning module 640, wherein:

[0142] A data acquisition module, used to acquire tunnel cable measurement data and tunnel cable environment data, wherein the tunnel cable measurement data and tunnel cable environment data are obtained based on data collected by multiple sensors;

[0143] A fault prediction module is used to use tunnel cable measurement data and tunnel cable environment data as input, call a trained fault prediction model, and determine the fault prediction time and fault prediction type of the tunnel cable. The fault prediction model is trained based on historical tunnel cable measurement data and historical tunnel cable environment data that carry fault time points and fault types.

[0144] A health assessment module, used to determine the cable health status score based on the tunnel cable measurement data, tunnel cable environment data and preset health status evaluation criteria;

[0145] The fault warning module is used to issue warnings based on the fault prediction time, fault prediction type and cable health status score.

[0146] Each module in the above-mentioned tunnel cable inspection device 600 can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0147] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 6As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a tunnel cable inspection method is implemented.

[0148] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0149] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps in any one of the above-mentioned tunnel cable inspection method embodiments are implemented.

[0150] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in any one of the above-mentioned tunnel cable inspection method embodiments are implemented.

[0151] In one embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps in any one of the above-mentioned tunnel cable inspection method embodiments.

[0152] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0153] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0154] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0155] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A tunnel cable inspection system, characterized in that: The system includes a sensor module, a monitoring and control platform, an edge computing node, a big data analysis platform, and an inspection robot equipped with multiple sensors: The sensor module collects tunnel cable environment data in real time, and sends the tunnel cable environment data to the edge computing node and the monitoring and control platform; The inspection robot moves according to a preset inspection path, obtains tunnel cable measurement data, and sends the tunnel cable measurement data to the edge computing node and the monitoring and control platform, wherein the tunnel cable measurement data is obtained based on data collected by multiple sensors; The edge computing node performs data preprocessing on the tunnel cable measurement data and the tunnel cable environment data to obtain target tunnel cable measurement data and target tunnel cable environment data, and sends the target tunnel cable measurement data and the target tunnel cable environment data to the big data analysis platform; The big data analysis platform performs fault prediction and health status assessment on the tunnel cable based on the target tunnel cable measurement data and the target tunnel cable environmental data, obtains fault prediction results and health status assessment results, and sends the fault prediction results and health status assessment results to the monitoring and control platform, and the monitoring and control platform visualizes the received data.

2. The tunnel cable inspection system according to claim 1, characterized in that: The edge computing node is also used to perform abnormality detection on the tunnel cable based on the target tunnel cable measurement data and the target tunnel cable environmental data to obtain an abnormality detection result. When the abnormal result indicates that the tunnel cable is abnormal, an alarm message is generated and sent to the monitoring and control platform.

3. The tunnel cable inspection system according to claim 1, characterized in that: The big data analysis platform is also used for: Taking the target tunnel cable measurement data and the target tunnel cable environment data as input, calling a trained fault prediction model to determine the fault prediction time and fault prediction type of the tunnel cable, wherein the trained fault prediction model is trained based on historical target tunnel cable measurement data and historical target tunnel cable environment data; Determine a cable health status score based on the target tunnel cable measurement data, the target tunnel cable environment data and a preset health status evaluation standard; The predicted fault time, the predicted fault type and the cable health status score are sent to the monitoring and control platform.

4. The tunnel cable inspection system according to any one of claims 1 to 3, characterized in that: The sensor module includes a temperature sensor, a humidity sensor, a vibration sensor and a current sensor: The temperature sensor is used to collect temperature data of the tunnel cable and send the temperature data to the edge computing node; The humidity sensor is used to collect humidity data of the tunnel cable and send the humidity data to the edge computing node; The vibration sensor is used to collect vibration data of the tunnel cable and send the vibration data to the edge computing node; The current sensor is used to collect current data of the tunnel cable and send the current data to the edge computing node. The tunnel cable environmental data includes the temperature data, humidity data, vibration data and current data.

5. The tunnel cable inspection system according to any one of claims 1 to 3, characterized in that: The inspection robot is equipped with a temperature sensor, a humidity sensor, a current sensor, a voltage sensor, a smoke sensor and an image sensor: The temperature sensor is used to collect temperature data of the tunnel cable and send the temperature data to the edge computing node; The humidity sensor is used to collect humidity data of the tunnel cable and send the humidity data to the edge computing node; The current sensor is used to collect current data of the tunnel cable and send the current data to the edge computing node; The voltage sensor is used to collect voltage data of the tunnel cable and send the voltage data to the edge computing node; The smoke sensor is used to collect smoke concentration data in the tunnel and send the smoke concentration data to the edge computing node; The image sensor is used to collect image data of the tunnel cable and send the image data to the edge computing node; The tunnel cable measurement data includes the temperature data, humidity data, voltage data and current data, concentration data and image data.

6. The tunnel cable inspection system according to claim 5, characterized in that: The inspection robot is also equipped with a laser radar sensor and an ultrasonic sensor, wherein: The laser radar sensor and the ultrasonic sensor are used to detect whether there are obstacles in the preset inspection path to obtain obstacle detection results, and the inspection robot is also used to perform obstacle avoidance operations based on the obstacle detection results.

7. The tunnel cable inspection system according to claim 3, characterized in that: The big data analysis platform is also used to generate maintenance suggestion information based on the fault prediction time and the fault prediction type, and send the maintenance suggestion information to the monitoring and control platform.

8. The tunnel cable inspection system according to claim 7, characterized in that: The monitoring and control platform is also used to push the alarm information after receiving the alarm information.

9. The tunnel cable inspection system according to claim 8, characterized in that: The monitoring and control platform also includes a control module, and the control module is used to remotely control the inspection robot.

10. A tunnel cable inspection method, characterized in that: A big data analysis platform applied to a tunnel cable inspection system according to any one of claims 1 to 9, the method comprising: Acquire tunnel cable measurement data and tunnel cable environment data, wherein the tunnel cable measurement data and the tunnel cable environment data are obtained based on data collected by multiple sensors; Taking the tunnel cable measurement data and the tunnel cable environment data as input, calling a trained fault prediction model to determine the fault prediction time and fault prediction type of the tunnel cable, wherein the fault prediction model is trained based on historical tunnel cable measurement data and historical tunnel cable environment data carrying the fault time point and fault type; Determining a cable health status score based on the tunnel cable measurement data, the tunnel cable environment data and a preset health status evaluation standard; An early warning is issued based on the predicted fault time, the predicted fault type and the cable health status score.

Images